{"task":"Text-based Image Editing","dataset":"PIE-Bench","metric_names":["Background PSNR","Background LPIPS","Structure Distance","CLIPSIM"],"rows":[{"id":13731,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"KV-Edit","metrics":{"Background LPIPS":"9.92","Background PSNR":"35.87","CLIPSIM":"25.63","Structure Distance":"1.98"},"paper_url":"https://arxiv.org/abs/2502.17363v1","paper_title":"KV-Edit: Training-Free Image Editing for Precise Background Preservation","paper_date":"2025-02-24","code_links":[{"title":"Xilluill/KV-Edit","url":"https://github.com/Xilluill/KV-Edit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":13732,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Virtual Inversion+Unified Attention Control+LCM","metrics":{"Background LPIPS":"47.58","Background PSNR":"28.51","CLIPSIM":"25.03","Structure Distance":"13.78"},"paper_url":"https://arxiv.org/abs/2312.04965v1","paper_title":"Inversion-Free Image Editing with Natural Language","paper_date":"2023-12-07","code_links":[{"title":"sled-group/InfEdit","url":"https://github.com/sled-group/InfEdit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":13733,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Virtual Inversion+ViMAEdit","metrics":{"Background LPIPS":"45.67","Background PSNR":"28.27","CLIPSIM":"25.91","Structure Distance":"12.65"},"paper_url":"https://arxiv.org/abs/2410.10496v2","paper_title":"Vision-guided and Mask-enhanced Adaptive Denoising for Prompt-based Image Editing","paper_date":"2024-10-14","code_links":[{"title":"Null-0000/ViMAEdit","url":"https://github.com/Null-0000/ViMAEdit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":13734,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Virtual Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"47.98","Background PSNR":"27.52","CLIPSIM":"24.89","Structure Distance":"14.22"},"paper_url":"https://arxiv.org/abs/2312.04965v1","paper_title":"Inversion-Free Image Editing with Natural Language","paper_date":"2023-12-07","code_links":[{"title":"sled-group/InfEdit","url":"https://github.com/sled-group/InfEdit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":13735,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Direct Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"54.55","Background PSNR":"27.22","CLIPSIM":"25.02","Structure Distance":"11.65"},"paper_url":"https://arxiv.org/abs/2310.01506v2","paper_title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","paper_date":"2023-10-02","code_links":[{"title":"cure-lab/pnpinversion","url":"https://github.com/cure-lab/pnpinversion"},{"title":"cure-lab/directinversion","url":"https://github.com/cure-lab/directinversion"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":13736,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Null-Text Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"60.67","Background PSNR":"27.03","CLIPSIM":"24.75","Structure Distance":"13.44"},"paper_url":"https://arxiv.org/abs/2211.09794v1","paper_title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","paper_date":"2022-11-17","code_links":[{"title":"google/prompt-to-prompt","url":"https://github.com/google/prompt-to-prompt"},{"title":"thepowerfuldeez/null-text-inversion","url":"https://github.com/thepowerfuldeez/null-text-inversion"},{"title":"phymhan/prompt-to-prompt","url":"https://github.com/phymhan/prompt-to-prompt"},{"title":"qwopqwop200/semantic-image-editing-with-null-inv","url":"https://github.com/qwopqwop200/semantic-image-editing-with-null-inv"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":13737,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Virtual Inversion+Prompt-to-Prompt+LCM","metrics":{"Background LPIPS":"55.85","Background PSNR":"26.64","CLIPSIM":"24.57","Structure Distance":"15.61"},"paper_url":"https://arxiv.org/abs/2312.04965v1","paper_title":"Inversion-Free Image Editing with Natural Language","paper_date":"2023-12-07","code_links":[{"title":"sled-group/InfEdit","url":"https://github.com/sled-group/InfEdit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":13738,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Negative-Prompt Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"69.01","Background PSNR":"26.21","CLIPSIM":"24.61","Structure Distance":"16.17"},"paper_url":"https://arxiv.org/abs/2305.16807v2","paper_title":"Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models","paper_date":"2023-05-26","code_links":[],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":13739,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"StyleDiffusion+Prompt-to-Prompt","metrics":{"Background LPIPS":"66.10","Background PSNR":"26.05","CLIPSIM":"24.78","Structure Distance":"11.65"},"paper_url":"https://arxiv.org/abs/2303.15649v3","paper_title":"StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing","paper_date":"2023-03-28","code_links":[{"title":"sen-mao/StyleDiffusion","url":"https://github.com/sen-mao/StyleDiffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":13740,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"FireFlow","metrics":{"Background LPIPS":"123.6","Background PSNR":"23.03","CLIPSIM":"26.02","Structure Distance":"27.1"},"paper_url":"https://arxiv.org/abs/2412.07517v1","paper_title":"FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing","paper_date":"2024-12-10","code_links":[{"title":"holmesshuan/fireflow","url":"https://github.com/holmesshuan/fireflow"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":13741,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Direct Inversion+MasaCtrl","metrics":{"Background LPIPS":"87.94","Background PSNR":"22.64","CLIPSIM":"24.38","Structure Distance":"24.70"},"paper_url":"https://arxiv.org/abs/2310.01506v2","paper_title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","paper_date":"2023-10-02","code_links":[{"title":"cure-lab/pnpinversion","url":"https://github.com/cure-lab/pnpinversion"},{"title":"cure-lab/directinversion","url":"https://github.com/cure-lab/directinversion"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":13742,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Direct Inversion+Plug-and-Play","metrics":{"Background LPIPS":"106.06","Background PSNR":"22.46","CLIPSIM":"25.41","Structure Distance":"24.29"},"paper_url":"https://arxiv.org/abs/2310.01506v2","paper_title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","paper_date":"2023-10-02","code_links":[{"title":"cure-lab/pnpinversion","url":"https://github.com/cure-lab/pnpinversion"},{"title":"cure-lab/directinversion","url":"https://github.com/cure-lab/directinversion"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":13743,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"DDIM Inversion+Plug-and-Play","metrics":{"Background LPIPS":"113.46","Background PSNR":"22.28","CLIPSIM":"25.41","Structure Distance":"28.22"},"paper_url":"https://arxiv.org/abs/2211.12572v1","paper_title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","paper_date":"2022-11-22","code_links":[{"title":"MichalGeyer/plug-and-play","url":"https://github.com/MichalGeyer/plug-and-play"},{"title":"Shilin-LU/TF-ICON","url":"https://github.com/Shilin-LU/TF-ICON"},{"title":"michalgeyer/pnp-diffusers","url":"https://github.com/michalgeyer/pnp-diffusers"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":13744,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"DDIM Inversion+MasaCtrl","metrics":{"Background LPIPS":"106.62","Background PSNR":"22.17","CLIPSIM":"23.96","Structure Distance":"28.38"},"paper_url":"https://arxiv.org/abs/2304.08465v1","paper_title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","paper_date":"2023-04-17","code_links":[{"title":"tencentarc/masactrl","url":"https://github.com/tencentarc/masactrl"},{"title":"phymhan/prompt-to-prompt","url":"https://github.com/phymhan/prompt-to-prompt"},{"title":"hansam95/nmg","url":"https://github.com/hansam95/nmg"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":13745,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Direct Inversion+Pix2Pix-Zero","metrics":{"Background LPIPS":"138.98","Background PSNR":"21.53","CLIPSIM":"23.31","Structure Distance":"49.22"},"paper_url":"https://arxiv.org/abs/2310.01506v2","paper_title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","paper_date":"2023-10-02","code_links":[{"title":"cure-lab/pnpinversion","url":"https://github.com/cure-lab/pnpinversion"},{"title":"cure-lab/directinversion","url":"https://github.com/cure-lab/directinversion"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":13746,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"DDIM Inversion+Pix2Pix-Zero","metrics":{"Background LPIPS":"172.22","Background PSNR":"20.44","CLIPSIM":"22.80","Structure Distance":"61.68"},"paper_url":"https://arxiv.org/abs/2302.03027v1","paper_title":"Zero-shot Image-to-Image Translation","paper_date":"2023-02-06","code_links":[{"title":"pix2pixzero/pix2pix-zero","url":"https://github.com/pix2pixzero/pix2pix-zero"},{"title":"hansam95/nmg","url":"https://github.com/hansam95/nmg"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":13747,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"DDIM Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"208.80","Background PSNR":"17.87","CLIPSIM":"25.01","Structure Distance":"69.43"},"paper_url":"https://arxiv.org/abs/2208.01626v1","paper_title":"Prompt-to-Prompt Image Editing with Cross Attention Control","paper_date":"2022-08-02","code_links":[{"title":"google/prompt-to-prompt","url":"https://github.com/google/prompt-to-prompt"},{"title":"bloc97/CrossAttentionControl","url":"https://github.com/bloc97/CrossAttentionControl"},{"title":"wandb/examples","url":"https://github.com/wandb/examples/blob/master/colabs/cross-attention-control/Cross_Attention_Control_WandB.ipynb"},{"title":"chenwu98/cycle-diffusion","url":"https://github.com/chenwu98/cycle-diffusion"},{"title":"phymhan/prompt-to-prompt","url":"https://github.com/phymhan/prompt-to-prompt"},{"title":"hansam95/nmg","url":"https://github.com/hansam95/nmg"},{"title":"miguelCalado/prompt-to-prompt-tensorflow","url":"https://github.com/miguelCalado/prompt-to-prompt-tensorflow"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":13748,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"FireFlow (Add Q)","metrics":{"Background LPIPS":"239.4","Background PSNR":"16.49","CLIPSIM":"27.33","Structure Distance":"70.9"},"paper_url":"https://arxiv.org/abs/2412.07517v1","paper_title":"FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing","paper_date":"2024-12-10","code_links":[{"title":"holmesshuan/fireflow","url":"https://github.com/holmesshuan/fireflow"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":113656,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"KV-Edit","metrics":{"Background LPIPS":"9.92","Background PSNR":"35.87","CLIPSIM":"25.63","Structure Distance":"1.98"},"paper_url":"https://arxiv.org/abs/2502.17363v1","paper_title":"KV-Edit: Training-Free Image Editing for Precise Background Preservation","paper_date":"2025-02-24","code_links":[{"title":"Xilluill/KV-Edit","url":"https://github.com/Xilluill/KV-Edit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":113657,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Virtual Inversion+Unified Attention Control+LCM","metrics":{"Background LPIPS":"47.58","Background PSNR":"28.51","CLIPSIM":"25.03","Structure Distance":"13.78"},"paper_url":"https://arxiv.org/abs/2312.04965v1","paper_title":"Inversion-Free Image Editing with Natural Language","paper_date":"2023-12-07","code_links":[{"title":"sled-group/InfEdit","url":"https://github.com/sled-group/InfEdit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":113658,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Virtual Inversion+ViMAEdit","metrics":{"Background LPIPS":"45.67","Background PSNR":"28.27","CLIPSIM":"25.91","Structure Distance":"12.65"},"paper_url":"https://arxiv.org/abs/2410.10496v2","paper_title":"Vision-guided and Mask-enhanced Adaptive Denoising for Prompt-based Image Editing","paper_date":"2024-10-14","code_links":[{"title":"Null-0000/ViMAEdit","url":"https://github.com/Null-0000/ViMAEdit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":113659,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Virtual Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"47.98","Background PSNR":"27.52","CLIPSIM":"24.89","Structure Distance":"14.22"},"paper_url":"https://arxiv.org/abs/2312.04965v1","paper_title":"Inversion-Free Image Editing with Natural Language","paper_date":"2023-12-07","code_links":[{"title":"sled-group/InfEdit","url":"https://github.com/sled-group/InfEdit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":113660,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Direct Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"54.55","Background PSNR":"27.22","CLIPSIM":"25.02","Structure Distance":"11.65"},"paper_url":"https://arxiv.org/abs/2310.01506v2","paper_title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","paper_date":"2023-10-02","code_links":[{"title":"cure-lab/pnpinversion","url":"https://github.com/cure-lab/pnpinversion"},{"title":"cure-lab/directinversion","url":"https://github.com/cure-lab/directinversion"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":113661,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Null-Text Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"60.67","Background PSNR":"27.03","CLIPSIM":"24.75","Structure Distance":"13.44"},"paper_url":"https://arxiv.org/abs/2211.09794v1","paper_title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","paper_date":"2022-11-17","code_links":[{"title":"google/prompt-to-prompt","url":"https://github.com/google/prompt-to-prompt"},{"title":"thepowerfuldeez/null-text-inversion","url":"https://github.com/thepowerfuldeez/null-text-inversion"},{"title":"phymhan/prompt-to-prompt","url":"https://github.com/phymhan/prompt-to-prompt"},{"title":"qwopqwop200/semantic-image-editing-with-null-inv","url":"https://github.com/qwopqwop200/semantic-image-editing-with-null-inv"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":113662,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Virtual Inversion+Prompt-to-Prompt+LCM","metrics":{"Background LPIPS":"55.85","Background PSNR":"26.64","CLIPSIM":"24.57","Structure Distance":"15.61"},"paper_url":"https://arxiv.org/abs/2312.04965v1","paper_title":"Inversion-Free Image Editing with Natural Language","paper_date":"2023-12-07","code_links":[{"title":"sled-group/InfEdit","url":"https://github.com/sled-group/InfEdit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":113663,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Negative-Prompt Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"69.01","Background PSNR":"26.21","CLIPSIM":"24.61","Structure Distance":"16.17"},"paper_url":"https://arxiv.org/abs/2305.16807v2","paper_title":"Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models","paper_date":"2023-05-26","code_links":[],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":113664,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"StyleDiffusion+Prompt-to-Prompt","metrics":{"Background LPIPS":"66.10","Background PSNR":"26.05","CLIPSIM":"24.78","Structure Distance":"11.65"},"paper_url":"https://arxiv.org/abs/2303.15649v3","paper_title":"StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing","paper_date":"2023-03-28","code_links":[{"title":"sen-mao/StyleDiffusion","url":"https://github.com/sen-mao/StyleDiffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":113665,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"FireFlow","metrics":{"Background LPIPS":"123.6","Background PSNR":"23.03","CLIPSIM":"26.02","Structure Distance":"27.1"},"paper_url":"https://arxiv.org/abs/2412.07517v1","paper_title":"FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing","paper_date":"2024-12-10","code_links":[{"title":"holmesshuan/fireflow","url":"https://github.com/holmesshuan/fireflow"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":113666,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Direct Inversion+MasaCtrl","metrics":{"Background LPIPS":"87.94","Background PSNR":"22.64","CLIPSIM":"24.38","Structure Distance":"24.70"},"paper_url":"https://arxiv.org/abs/2310.01506v2","paper_title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","paper_date":"2023-10-02","code_links":[{"title":"cure-lab/pnpinversion","url":"https://github.com/cure-lab/pnpinversion"},{"title":"cure-lab/directinversion","url":"https://github.com/cure-lab/directinversion"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":113667,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Direct Inversion+Plug-and-Play","metrics":{"Background LPIPS":"106.06","Background PSNR":"22.46","CLIPSIM":"25.41","Structure Distance":"24.29"},"paper_url":"https://arxiv.org/abs/2310.01506v2","paper_title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","paper_date":"2023-10-02","code_links":[{"title":"cure-lab/pnpinversion","url":"https://github.com/cure-lab/pnpinversion"},{"title":"cure-lab/directinversion","url":"https://github.com/cure-lab/directinversion"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":113668,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"DDIM Inversion+Plug-and-Play","metrics":{"Background LPIPS":"113.46","Background PSNR":"22.28","CLIPSIM":"25.41","Structure Distance":"28.22"},"paper_url":"https://arxiv.org/abs/2211.12572v1","paper_title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","paper_date":"2022-11-22","code_links":[{"title":"MichalGeyer/plug-and-play","url":"https://github.com/MichalGeyer/plug-and-play"},{"title":"Shilin-LU/TF-ICON","url":"https://github.com/Shilin-LU/TF-ICON"},{"title":"michalgeyer/pnp-diffusers","url":"https://github.com/michalgeyer/pnp-diffusers"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":113669,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"DDIM Inversion+MasaCtrl","metrics":{"Background LPIPS":"106.62","Background PSNR":"22.17","CLIPSIM":"23.96","Structure Distance":"28.38"},"paper_url":"https://arxiv.org/abs/2304.08465v1","paper_title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","paper_date":"2023-04-17","code_links":[{"title":"tencentarc/masactrl","url":"https://github.com/tencentarc/masactrl"},{"title":"phymhan/prompt-to-prompt","url":"https://github.com/phymhan/prompt-to-prompt"},{"title":"hansam95/nmg","url":"https://github.com/hansam95/nmg"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":113670,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Direct Inversion+Pix2Pix-Zero","metrics":{"Background LPIPS":"138.98","Background PSNR":"21.53","CLIPSIM":"23.31","Structure Distance":"49.22"},"paper_url":"https://arxiv.org/abs/2310.01506v2","paper_title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","paper_date":"2023-10-02","code_links":[{"title":"cure-lab/pnpinversion","url":"https://github.com/cure-lab/pnpinversion"},{"title":"cure-lab/directinversion","url":"https://github.com/cure-lab/directinversion"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":113671,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"DDIM Inversion+Pix2Pix-Zero","metrics":{"Background LPIPS":"172.22","Background PSNR":"20.44","CLIPSIM":"22.80","Structure Distance":"61.68"},"paper_url":"https://arxiv.org/abs/2302.03027v1","paper_title":"Zero-shot Image-to-Image Translation","paper_date":"2023-02-06","code_links":[{"title":"pix2pixzero/pix2pix-zero","url":"https://github.com/pix2pixzero/pix2pix-zero"},{"title":"hansam95/nmg","url":"https://github.com/hansam95/nmg"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":113672,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"DDIM Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"208.80","Background PSNR":"17.87","CLIPSIM":"25.01","Structure Distance":"69.43"},"paper_url":"https://arxiv.org/abs/2208.01626v1","paper_title":"Prompt-to-Prompt Image Editing with Cross Attention Control","paper_date":"2022-08-02","code_links":[{"title":"google/prompt-to-prompt","url":"https://github.com/google/prompt-to-prompt"},{"title":"bloc97/CrossAttentionControl","url":"https://github.com/bloc97/CrossAttentionControl"},{"title":"wandb/examples","url":"https://github.com/wandb/examples/blob/master/colabs/cross-attention-control/Cross_Attention_Control_WandB.ipynb"},{"title":"chenwu98/cycle-diffusion","url":"https://github.com/chenwu98/cycle-diffusion"},{"title":"phymhan/prompt-to-prompt","url":"https://github.com/phymhan/prompt-to-prompt"},{"title":"hansam95/nmg","url":"https://github.com/hansam95/nmg"},{"title":"miguelCalado/prompt-to-prompt-tensorflow","url":"https://github.com/miguelCalado/prompt-to-prompt-tensorflow"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":113673,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"FireFlow (Add Q)","metrics":{"Background LPIPS":"239.4","Background PSNR":"16.49","CLIPSIM":"27.33","Structure Distance":"70.9"},"paper_url":"https://arxiv.org/abs/2412.07517v1","paper_title":"FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing","paper_date":"2024-12-10","code_links":[{"title":"holmesshuan/fireflow","url":"https://github.com/holmesshuan/fireflow"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":129984,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"KV-Edit","metrics":{"Background LPIPS":"9.92","Background PSNR":"35.87","CLIPSIM":"25.63","Structure Distance":"1.98"},"paper_url":"https://arxiv.org/abs/2502.17363v1","paper_title":"KV-Edit: Training-Free Image Editing for Precise Background Preservation","paper_date":"2025-02-24","code_links":[{"title":"Xilluill/KV-Edit","url":"https://github.com/Xilluill/KV-Edit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":129985,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Virtual Inversion+Unified Attention Control+LCM","metrics":{"Background LPIPS":"47.58","Background PSNR":"28.51","CLIPSIM":"25.03","Structure Distance":"13.78"},"paper_url":"https://arxiv.org/abs/2312.04965v1","paper_title":"Inversion-Free Image Editing with Natural Language","paper_date":"2023-12-07","code_links":[{"title":"sled-group/InfEdit","url":"https://github.com/sled-group/InfEdit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":129986,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Virtual Inversion+ViMAEdit","metrics":{"Background LPIPS":"45.67","Background PSNR":"28.27","CLIPSIM":"25.91","Structure Distance":"12.65"},"paper_url":"https://arxiv.org/abs/2410.10496v2","paper_title":"Vision-guided and Mask-enhanced Adaptive Denoising for Prompt-based Image Editing","paper_date":"2024-10-14","code_links":[{"title":"Null-0000/ViMAEdit","url":"https://github.com/Null-0000/ViMAEdit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":129987,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Virtual Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"47.98","Background PSNR":"27.52","CLIPSIM":"24.89","Structure Distance":"14.22"},"paper_url":"https://arxiv.org/abs/2312.04965v1","paper_title":"Inversion-Free Image Editing with Natural Language","paper_date":"2023-12-07","code_links":[{"title":"sled-group/InfEdit","url":"https://github.com/sled-group/InfEdit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":129988,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Direct Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"54.55","Background PSNR":"27.22","CLIPSIM":"25.02","Structure Distance":"11.65"},"paper_url":"https://arxiv.org/abs/2310.01506v2","paper_title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","paper_date":"2023-10-02","code_links":[{"title":"cure-lab/pnpinversion","url":"https://github.com/cure-lab/pnpinversion"},{"title":"cure-lab/directinversion","url":"https://github.com/cure-lab/directinversion"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":129989,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Null-Text Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"60.67","Background PSNR":"27.03","CLIPSIM":"24.75","Structure Distance":"13.44"},"paper_url":"https://arxiv.org/abs/2211.09794v1","paper_title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","paper_date":"2022-11-17","code_links":[{"title":"google/prompt-to-prompt","url":"https://github.com/google/prompt-to-prompt"},{"title":"thepowerfuldeez/null-text-inversion","url":"https://github.com/thepowerfuldeez/null-text-inversion"},{"title":"phymhan/prompt-to-prompt","url":"https://github.com/phymhan/prompt-to-prompt"},{"title":"qwopqwop200/semantic-image-editing-with-null-inv","url":"https://github.com/qwopqwop200/semantic-image-editing-with-null-inv"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":129990,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Virtual Inversion+Prompt-to-Prompt+LCM","metrics":{"Background LPIPS":"55.85","Background PSNR":"26.64","CLIPSIM":"24.57","Structure Distance":"15.61"},"paper_url":"https://arxiv.org/abs/2312.04965v1","paper_title":"Inversion-Free Image Editing with Natural Language","paper_date":"2023-12-07","code_links":[{"title":"sled-group/InfEdit","url":"https://github.com/sled-group/InfEdit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":129991,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Negative-Prompt Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"69.01","Background PSNR":"26.21","CLIPSIM":"24.61","Structure Distance":"16.17"},"paper_url":"https://arxiv.org/abs/2305.16807v2","paper_title":"Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models","paper_date":"2023-05-26","code_links":[],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":129992,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"StyleDiffusion+Prompt-to-Prompt","metrics":{"Background LPIPS":"66.10","Background PSNR":"26.05","CLIPSIM":"24.78","Structure Distance":"11.65"},"paper_url":"https://arxiv.org/abs/2303.15649v3","paper_title":"StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing","paper_date":"2023-03-28","code_links":[{"title":"sen-mao/StyleDiffusion","url":"https://github.com/sen-mao/StyleDiffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":129993,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"FireFlow","metrics":{"Background LPIPS":"123.6","Background PSNR":"23.03","CLIPSIM":"26.02","Structure Distance":"27.1"},"paper_url":"https://arxiv.org/abs/2412.07517v1","paper_title":"FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing","paper_date":"2024-12-10","code_links":[{"title":"holmesshuan/fireflow","url":"https://github.com/holmesshuan/fireflow"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":129994,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Direct Inversion+MasaCtrl","metrics":{"Background LPIPS":"87.94","Background PSNR":"22.64","CLIPSIM":"24.38","Structure Distance":"24.70"},"paper_url":"https://arxiv.org/abs/2310.01506v2","paper_title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","paper_date":"2023-10-02","code_links":[{"title":"cure-lab/pnpinversion","url":"https://github.com/cure-lab/pnpinversion"},{"title":"cure-lab/directinversion","url":"https://github.com/cure-lab/directinversion"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":129995,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Direct Inversion+Plug-and-Play","metrics":{"Background LPIPS":"106.06","Background PSNR":"22.46","CLIPSIM":"25.41","Structure Distance":"24.29"},"paper_url":"https://arxiv.org/abs/2310.01506v2","paper_title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","paper_date":"2023-10-02","code_links":[{"title":"cure-lab/pnpinversion","url":"https://github.com/cure-lab/pnpinversion"},{"title":"cure-lab/directinversion","url":"https://github.com/cure-lab/directinversion"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":129996,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"DDIM Inversion+Plug-and-Play","metrics":{"Background LPIPS":"113.46","Background PSNR":"22.28","CLIPSIM":"25.41","Structure Distance":"28.22"},"paper_url":"https://arxiv.org/abs/2211.12572v1","paper_title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","paper_date":"2022-11-22","code_links":[{"title":"MichalGeyer/plug-and-play","url":"https://github.com/MichalGeyer/plug-and-play"},{"title":"Shilin-LU/TF-ICON","url":"https://github.com/Shilin-LU/TF-ICON"},{"title":"michalgeyer/pnp-diffusers","url":"https://github.com/michalgeyer/pnp-diffusers"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":129997,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"DDIM Inversion+MasaCtrl","metrics":{"Background LPIPS":"106.62","Background PSNR":"22.17","CLIPSIM":"23.96","Structure Distance":"28.38"},"paper_url":"https://arxiv.org/abs/2304.08465v1","paper_title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","paper_date":"2023-04-17","code_links":[{"title":"tencentarc/masactrl","url":"https://github.com/tencentarc/masactrl"},{"title":"phymhan/prompt-to-prompt","url":"https://github.com/phymhan/prompt-to-prompt"},{"title":"hansam95/nmg","url":"https://github.com/hansam95/nmg"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":129998,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Direct Inversion+Pix2Pix-Zero","metrics":{"Background LPIPS":"138.98","Background PSNR":"21.53","CLIPSIM":"23.31","Structure Distance":"49.22"},"paper_url":"https://arxiv.org/abs/2310.01506v2","paper_title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","paper_date":"2023-10-02","code_links":[{"title":"cure-lab/pnpinversion","url":"https://github.com/cure-lab/pnpinversion"},{"title":"cure-lab/directinversion","url":"https://github.com/cure-lab/directinversion"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":129999,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"DDIM Inversion+Pix2Pix-Zero","metrics":{"Background LPIPS":"172.22","Background PSNR":"20.44","CLIPSIM":"22.80","Structure Distance":"61.68"},"paper_url":"https://arxiv.org/abs/2302.03027v1","paper_title":"Zero-shot Image-to-Image Translation","paper_date":"2023-02-06","code_links":[{"title":"pix2pixzero/pix2pix-zero","url":"https://github.com/pix2pixzero/pix2pix-zero"},{"title":"hansam95/nmg","url":"https://github.com/hansam95/nmg"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":130000,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"DDIM Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"208.80","Background PSNR":"17.87","CLIPSIM":"25.01","Structure Distance":"69.43"},"paper_url":"https://arxiv.org/abs/2208.01626v1","paper_title":"Prompt-to-Prompt Image Editing with Cross Attention Control","paper_date":"2022-08-02","code_links":[{"title":"google/prompt-to-prompt","url":"https://github.com/google/prompt-to-prompt"},{"title":"bloc97/CrossAttentionControl","url":"https://github.com/bloc97/CrossAttentionControl"},{"title":"wandb/examples","url":"https://github.com/wandb/examples/blob/master/colabs/cross-attention-control/Cross_Attention_Control_WandB.ipynb"},{"title":"chenwu98/cycle-diffusion","url":"https://github.com/chenwu98/cycle-diffusion"},{"title":"phymhan/prompt-to-prompt","url":"https://github.com/phymhan/prompt-to-prompt"},{"title":"hansam95/nmg","url":"https://github.com/hansam95/nmg"},{"title":"miguelCalado/prompt-to-prompt-tensorflow","url":"https://github.com/miguelCalado/prompt-to-prompt-tensorflow"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":130001,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"FireFlow (Add Q)","metrics":{"Background LPIPS":"239.4","Background PSNR":"16.49","CLIPSIM":"27.33","Structure Distance":"70.9"},"paper_url":"https://arxiv.org/abs/2412.07517v1","paper_title":"FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing","paper_date":"2024-12-10","code_links":[{"title":"holmesshuan/fireflow","url":"https://github.com/holmesshuan/fireflow"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":140750,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"KV-Edit","metrics":{"Background LPIPS":"9.92","Background PSNR":"35.87","CLIPSIM":"25.63","Structure Distance":"1.98"},"paper_url":"https://arxiv.org/abs/2502.17363v1","paper_title":"KV-Edit: Training-Free Image Editing for Precise Background Preservation","paper_date":"2025-02-24","code_links":[{"title":"Xilluill/KV-Edit","url":"https://github.com/Xilluill/KV-Edit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":140751,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Virtual Inversion+Unified Attention Control+LCM","metrics":{"Background LPIPS":"47.58","Background PSNR":"28.51","CLIPSIM":"25.03","Structure Distance":"13.78"},"paper_url":"https://arxiv.org/abs/2312.04965v1","paper_title":"Inversion-Free Image Editing with Natural Language","paper_date":"2023-12-07","code_links":[{"title":"sled-group/InfEdit","url":"https://github.com/sled-group/InfEdit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":140752,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Virtual Inversion+ViMAEdit","metrics":{"Background LPIPS":"45.67","Background PSNR":"28.27","CLIPSIM":"25.91","Structure Distance":"12.65"},"paper_url":"https://arxiv.org/abs/2410.10496v2","paper_title":"Vision-guided and Mask-enhanced Adaptive Denoising for Prompt-based Image Editing","paper_date":"2024-10-14","code_links":[{"title":"Null-0000/ViMAEdit","url":"https://github.com/Null-0000/ViMAEdit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":140753,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Virtual Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"47.98","Background PSNR":"27.52","CLIPSIM":"24.89","Structure Distance":"14.22"},"paper_url":"https://arxiv.org/abs/2312.04965v1","paper_title":"Inversion-Free Image Editing with Natural Language","paper_date":"2023-12-07","code_links":[{"title":"sled-group/InfEdit","url":"https://github.com/sled-group/InfEdit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":140754,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Direct Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"54.55","Background PSNR":"27.22","CLIPSIM":"25.02","Structure Distance":"11.65"},"paper_url":"https://arxiv.org/abs/2310.01506v2","paper_title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","paper_date":"2023-10-02","code_links":[{"title":"cure-lab/pnpinversion","url":"https://github.com/cure-lab/pnpinversion"},{"title":"cure-lab/directinversion","url":"https://github.com/cure-lab/directinversion"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":140755,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Null-Text Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"60.67","Background PSNR":"27.03","CLIPSIM":"24.75","Structure Distance":"13.44"},"paper_url":"https://arxiv.org/abs/2211.09794v1","paper_title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","paper_date":"2022-11-17","code_links":[{"title":"google/prompt-to-prompt","url":"https://github.com/google/prompt-to-prompt"},{"title":"thepowerfuldeez/null-text-inversion","url":"https://github.com/thepowerfuldeez/null-text-inversion"},{"title":"phymhan/prompt-to-prompt","url":"https://github.com/phymhan/prompt-to-prompt"},{"title":"qwopqwop200/semantic-image-editing-with-null-inv","url":"https://github.com/qwopqwop200/semantic-image-editing-with-null-inv"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":140756,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Virtual Inversion+Prompt-to-Prompt+LCM","metrics":{"Background LPIPS":"55.85","Background PSNR":"26.64","CLIPSIM":"24.57","Structure Distance":"15.61"},"paper_url":"https://arxiv.org/abs/2312.04965v1","paper_title":"Inversion-Free Image Editing with Natural Language","paper_date":"2023-12-07","code_links":[{"title":"sled-group/InfEdit","url":"https://github.com/sled-group/InfEdit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":140757,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Negative-Prompt Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"69.01","Background PSNR":"26.21","CLIPSIM":"24.61","Structure Distance":"16.17"},"paper_url":"https://arxiv.org/abs/2305.16807v2","paper_title":"Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models","paper_date":"2023-05-26","code_links":[],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":140758,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"StyleDiffusion+Prompt-to-Prompt","metrics":{"Background LPIPS":"66.10","Background PSNR":"26.05","CLIPSIM":"24.78","Structure Distance":"11.65"},"paper_url":"https://arxiv.org/abs/2303.15649v3","paper_title":"StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing","paper_date":"2023-03-28","code_links":[{"title":"sen-mao/StyleDiffusion","url":"https://github.com/sen-mao/StyleDiffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":140759,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"FireFlow","metrics":{"Background LPIPS":"123.6","Background PSNR":"23.03","CLIPSIM":"26.02","Structure Distance":"27.1"},"paper_url":"https://arxiv.org/abs/2412.07517v1","paper_title":"FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing","paper_date":"2024-12-10","code_links":[{"title":"holmesshuan/fireflow","url":"https://github.com/holmesshuan/fireflow"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":140760,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Direct Inversion+MasaCtrl","metrics":{"Background LPIPS":"87.94","Background PSNR":"22.64","CLIPSIM":"24.38","Structure Distance":"24.70"},"paper_url":"https://arxiv.org/abs/2310.01506v2","paper_title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","paper_date":"2023-10-02","code_links":[{"title":"cure-lab/pnpinversion","url":"https://github.com/cure-lab/pnpinversion"},{"title":"cure-lab/directinversion","url":"https://github.com/cure-lab/directinversion"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":140761,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Direct Inversion+Plug-and-Play","metrics":{"Background LPIPS":"106.06","Background PSNR":"22.46","CLIPSIM":"25.41","Structure Distance":"24.29"},"paper_url":"https://arxiv.org/abs/2310.01506v2","paper_title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","paper_date":"2023-10-02","code_links":[{"title":"cure-lab/pnpinversion","url":"https://github.com/cure-lab/pnpinversion"},{"title":"cure-lab/directinversion","url":"https://github.com/cure-lab/directinversion"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":140762,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"DDIM Inversion+Plug-and-Play","metrics":{"Background LPIPS":"113.46","Background PSNR":"22.28","CLIPSIM":"25.41","Structure Distance":"28.22"},"paper_url":"https://arxiv.org/abs/2211.12572v1","paper_title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","paper_date":"2022-11-22","code_links":[{"title":"MichalGeyer/plug-and-play","url":"https://github.com/MichalGeyer/plug-and-play"},{"title":"Shilin-LU/TF-ICON","url":"https://github.com/Shilin-LU/TF-ICON"},{"title":"michalgeyer/pnp-diffusers","url":"https://github.com/michalgeyer/pnp-diffusers"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":140763,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"DDIM Inversion+MasaCtrl","metrics":{"Background LPIPS":"106.62","Background PSNR":"22.17","CLIPSIM":"23.96","Structure Distance":"28.38"},"paper_url":"https://arxiv.org/abs/2304.08465v1","paper_title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","paper_date":"2023-04-17","code_links":[{"title":"tencentarc/masactrl","url":"https://github.com/tencentarc/masactrl"},{"title":"phymhan/prompt-to-prompt","url":"https://github.com/phymhan/prompt-to-prompt"},{"title":"hansam95/nmg","url":"https://github.com/hansam95/nmg"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":140764,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Direct Inversion+Pix2Pix-Zero","metrics":{"Background LPIPS":"138.98","Background PSNR":"21.53","CLIPSIM":"23.31","Structure Distance":"49.22"},"paper_url":"https://arxiv.org/abs/2310.01506v2","paper_title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","paper_date":"2023-10-02","code_links":[{"title":"cure-lab/pnpinversion","url":"https://github.com/cure-lab/pnpinversion"},{"title":"cure-lab/directinversion","url":"https://github.com/cure-lab/directinversion"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":140765,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"DDIM Inversion+Pix2Pix-Zero","metrics":{"Background LPIPS":"172.22","Background PSNR":"20.44","CLIPSIM":"22.80","Structure Distance":"61.68"},"paper_url":"https://arxiv.org/abs/2302.03027v1","paper_title":"Zero-shot Image-to-Image Translation","paper_date":"2023-02-06","code_links":[{"title":"pix2pixzero/pix2pix-zero","url":"https://github.com/pix2pixzero/pix2pix-zero"},{"title":"hansam95/nmg","url":"https://github.com/hansam95/nmg"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":140766,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"DDIM Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"208.80","Background PSNR":"17.87","CLIPSIM":"25.01","Structure Distance":"69.43"},"paper_url":"https://arxiv.org/abs/2208.01626v1","paper_title":"Prompt-to-Prompt Image Editing with Cross Attention Control","paper_date":"2022-08-02","code_links":[{"title":"google/prompt-to-prompt","url":"https://github.com/google/prompt-to-prompt"},{"title":"bloc97/CrossAttentionControl","url":"https://github.com/bloc97/CrossAttentionControl"},{"title":"wandb/examples","url":"https://github.com/wandb/examples/blob/master/colabs/cross-attention-control/Cross_Attention_Control_WandB.ipynb"},{"title":"chenwu98/cycle-diffusion","url":"https://github.com/chenwu98/cycle-diffusion"},{"title":"phymhan/prompt-to-prompt","url":"https://github.com/phymhan/prompt-to-prompt"},{"title":"hansam95/nmg","url":"https://github.com/hansam95/nmg"},{"title":"miguelCalado/prompt-to-prompt-tensorflow","url":"https://github.com/miguelCalado/prompt-to-prompt-tensorflow"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":140767,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"FireFlow (Add Q)","metrics":{"Background LPIPS":"239.4","Background PSNR":"16.49","CLIPSIM":"27.33","Structure Distance":"70.9"},"paper_url":"https://arxiv.org/abs/2412.07517v1","paper_title":"FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing","paper_date":"2024-12-10","code_links":[{"title":"holmesshuan/fireflow","url":"https://github.com/holmesshuan/fireflow"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":148794,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"KV-Edit","metrics":{"Background LPIPS":"9.92","Background PSNR":"35.87","CLIPSIM":"25.63","Structure Distance":"1.98"},"paper_url":"https://arxiv.org/abs/2502.17363v1","paper_title":"KV-Edit: Training-Free Image Editing for Precise Background Preservation","paper_date":"2025-02-24","code_links":[{"title":"Xilluill/KV-Edit","url":"https://github.com/Xilluill/KV-Edit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":148795,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Virtual Inversion+Unified Attention Control+LCM","metrics":{"Background LPIPS":"47.58","Background PSNR":"28.51","CLIPSIM":"25.03","Structure Distance":"13.78"},"paper_url":"https://arxiv.org/abs/2312.04965v1","paper_title":"Inversion-Free Image Editing with Natural Language","paper_date":"2023-12-07","code_links":[{"title":"sled-group/InfEdit","url":"https://github.com/sled-group/InfEdit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":148796,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Virtual Inversion+ViMAEdit","metrics":{"Background LPIPS":"45.67","Background PSNR":"28.27","CLIPSIM":"25.91","Structure Distance":"12.65"},"paper_url":"https://arxiv.org/abs/2410.10496v2","paper_title":"Vision-guided and Mask-enhanced Adaptive Denoising for Prompt-based Image Editing","paper_date":"2024-10-14","code_links":[{"title":"Null-0000/ViMAEdit","url":"https://github.com/Null-0000/ViMAEdit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":148797,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Virtual Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"47.98","Background PSNR":"27.52","CLIPSIM":"24.89","Structure Distance":"14.22"},"paper_url":"https://arxiv.org/abs/2312.04965v1","paper_title":"Inversion-Free Image Editing with Natural Language","paper_date":"2023-12-07","code_links":[{"title":"sled-group/InfEdit","url":"https://github.com/sled-group/InfEdit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":148798,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Direct Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"54.55","Background PSNR":"27.22","CLIPSIM":"25.02","Structure Distance":"11.65"},"paper_url":"https://arxiv.org/abs/2310.01506v2","paper_title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","paper_date":"2023-10-02","code_links":[{"title":"cure-lab/pnpinversion","url":"https://github.com/cure-lab/pnpinversion"},{"title":"cure-lab/directinversion","url":"https://github.com/cure-lab/directinversion"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":148799,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Null-Text Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"60.67","Background PSNR":"27.03","CLIPSIM":"24.75","Structure Distance":"13.44"},"paper_url":"https://arxiv.org/abs/2211.09794v1","paper_title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","paper_date":"2022-11-17","code_links":[{"title":"google/prompt-to-prompt","url":"https://github.com/google/prompt-to-prompt"},{"title":"thepowerfuldeez/null-text-inversion","url":"https://github.com/thepowerfuldeez/null-text-inversion"},{"title":"phymhan/prompt-to-prompt","url":"https://github.com/phymhan/prompt-to-prompt"},{"title":"qwopqwop200/semantic-image-editing-with-null-inv","url":"https://github.com/qwopqwop200/semantic-image-editing-with-null-inv"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":148800,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Virtual Inversion+Prompt-to-Prompt+LCM","metrics":{"Background LPIPS":"55.85","Background PSNR":"26.64","CLIPSIM":"24.57","Structure Distance":"15.61"},"paper_url":"https://arxiv.org/abs/2312.04965v1","paper_title":"Inversion-Free Image Editing with Natural Language","paper_date":"2023-12-07","code_links":[{"title":"sled-group/InfEdit","url":"https://github.com/sled-group/InfEdit"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":148801,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Negative-Prompt Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"69.01","Background PSNR":"26.21","CLIPSIM":"24.61","Structure Distance":"16.17"},"paper_url":"https://arxiv.org/abs/2305.16807v2","paper_title":"Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models","paper_date":"2023-05-26","code_links":[],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":148802,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"StyleDiffusion+Prompt-to-Prompt","metrics":{"Background LPIPS":"66.10","Background PSNR":"26.05","CLIPSIM":"24.78","Structure Distance":"11.65"},"paper_url":"https://arxiv.org/abs/2303.15649v3","paper_title":"StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing","paper_date":"2023-03-28","code_links":[{"title":"sen-mao/StyleDiffusion","url":"https://github.com/sen-mao/StyleDiffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":148803,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"FireFlow","metrics":{"Background LPIPS":"123.6","Background PSNR":"23.03","CLIPSIM":"26.02","Structure Distance":"27.1"},"paper_url":"https://arxiv.org/abs/2412.07517v1","paper_title":"FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing","paper_date":"2024-12-10","code_links":[{"title":"holmesshuan/fireflow","url":"https://github.com/holmesshuan/fireflow"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":148804,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Direct Inversion+MasaCtrl","metrics":{"Background LPIPS":"87.94","Background PSNR":"22.64","CLIPSIM":"24.38","Structure Distance":"24.70"},"paper_url":"https://arxiv.org/abs/2310.01506v2","paper_title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","paper_date":"2023-10-02","code_links":[{"title":"cure-lab/pnpinversion","url":"https://github.com/cure-lab/pnpinversion"},{"title":"cure-lab/directinversion","url":"https://github.com/cure-lab/directinversion"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":148805,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Direct Inversion+Plug-and-Play","metrics":{"Background LPIPS":"106.06","Background PSNR":"22.46","CLIPSIM":"25.41","Structure Distance":"24.29"},"paper_url":"https://arxiv.org/abs/2310.01506v2","paper_title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","paper_date":"2023-10-02","code_links":[{"title":"cure-lab/pnpinversion","url":"https://github.com/cure-lab/pnpinversion"},{"title":"cure-lab/directinversion","url":"https://github.com/cure-lab/directinversion"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":148806,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"DDIM Inversion+Plug-and-Play","metrics":{"Background LPIPS":"113.46","Background PSNR":"22.28","CLIPSIM":"25.41","Structure Distance":"28.22"},"paper_url":"https://arxiv.org/abs/2211.12572v1","paper_title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","paper_date":"2022-11-22","code_links":[{"title":"MichalGeyer/plug-and-play","url":"https://github.com/MichalGeyer/plug-and-play"},{"title":"Shilin-LU/TF-ICON","url":"https://github.com/Shilin-LU/TF-ICON"},{"title":"michalgeyer/pnp-diffusers","url":"https://github.com/michalgeyer/pnp-diffusers"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":148807,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"DDIM Inversion+MasaCtrl","metrics":{"Background LPIPS":"106.62","Background PSNR":"22.17","CLIPSIM":"23.96","Structure Distance":"28.38"},"paper_url":"https://arxiv.org/abs/2304.08465v1","paper_title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","paper_date":"2023-04-17","code_links":[{"title":"tencentarc/masactrl","url":"https://github.com/tencentarc/masactrl"},{"title":"phymhan/prompt-to-prompt","url":"https://github.com/phymhan/prompt-to-prompt"},{"title":"hansam95/nmg","url":"https://github.com/hansam95/nmg"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":148808,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"Direct Inversion+Pix2Pix-Zero","metrics":{"Background LPIPS":"138.98","Background PSNR":"21.53","CLIPSIM":"23.31","Structure Distance":"49.22"},"paper_url":"https://arxiv.org/abs/2310.01506v2","paper_title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","paper_date":"2023-10-02","code_links":[{"title":"cure-lab/pnpinversion","url":"https://github.com/cure-lab/pnpinversion"},{"title":"cure-lab/directinversion","url":"https://github.com/cure-lab/directinversion"},{"title":"thu-cvml/texturediffusion","url":"https://github.com/thu-cvml/texturediffusion"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":148809,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"DDIM Inversion+Pix2Pix-Zero","metrics":{"Background LPIPS":"172.22","Background PSNR":"20.44","CLIPSIM":"22.80","Structure Distance":"61.68"},"paper_url":"https://arxiv.org/abs/2302.03027v1","paper_title":"Zero-shot Image-to-Image Translation","paper_date":"2023-02-06","code_links":[{"title":"pix2pixzero/pix2pix-zero","url":"https://github.com/pix2pixzero/pix2pix-zero"},{"title":"hansam95/nmg","url":"https://github.com/hansam95/nmg"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":148810,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"DDIM Inversion+Prompt-to-Prompt","metrics":{"Background LPIPS":"208.80","Background PSNR":"17.87","CLIPSIM":"25.01","Structure Distance":"69.43"},"paper_url":"https://arxiv.org/abs/2208.01626v1","paper_title":"Prompt-to-Prompt Image Editing with Cross Attention Control","paper_date":"2022-08-02","code_links":[{"title":"google/prompt-to-prompt","url":"https://github.com/google/prompt-to-prompt"},{"title":"bloc97/CrossAttentionControl","url":"https://github.com/bloc97/CrossAttentionControl"},{"title":"wandb/examples","url":"https://github.com/wandb/examples/blob/master/colabs/cross-attention-control/Cross_Attention_Control_WandB.ipynb"},{"title":"chenwu98/cycle-diffusion","url":"https://github.com/chenwu98/cycle-diffusion"},{"title":"phymhan/prompt-to-prompt","url":"https://github.com/phymhan/prompt-to-prompt"},{"title":"hansam95/nmg","url":"https://github.com/hansam95/nmg"},{"title":"miguelCalado/prompt-to-prompt-tensorflow","url":"https://github.com/miguelCalado/prompt-to-prompt-tensorflow"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":148811,"task":"Text-based Image Editing","parent_task":"Text-to-Image Generation","dataset":"PIE-Bench","model_name":"FireFlow (Add Q)","metrics":{"Background LPIPS":"239.4","Background PSNR":"16.49","CLIPSIM":"27.33","Structure Distance":"70.9"},"paper_url":"https://arxiv.org/abs/2412.07517v1","paper_title":"FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing","paper_date":"2024-12-10","code_links":[{"title":"holmesshuan/fireflow","url":"https://github.com/holmesshuan/fireflow"}],"metrics_order":"[\"Background PSNR\", \"Background LPIPS\", \"Structure Distance\", \"CLIPSIM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]}]}